© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5801
    Prev
    Next
    INDEX
    Explanations

    words that indicate aspects of medical studies and physical attributes of people

    oai_token-act-pair · gemini-2.0-flash

    hair

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.43
     الرياضيه
    -0.41
    オク
    -0.38
    ipedi
    -0.37
    ULATION
    -0.37
     fill
    -0.36
    ージャー
    -0.36
     marked
    -0.33
    phthal
    -0.33
    Географи
    -0.33
    POSITIVE LOGITS
     hair
    0.95
    tagHelperRunner
    0.91
     Hair
    0.88
    +#+#
    0.87
     HAIR
    0.85
    hair
    0.83
    expandindo
    0.82
     Hairst
    0.81
    Hair
    0.80
     hairstyle
    0.77
    Activations Density 0.663%

    No Known Activations